© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11886
    Prev
    Next
    INDEX
    Explanations

    technical terms and actions related to processes in computing and data transfer

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    mathematical symbols and equations

    np_acts-logits-general · gemini-2.0-flash

    numerical conditions and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    GEBURTSDATUM
    -0.44
    rungsseite
    -0.41
     finnas
    -0.40
    новништво
    -0.40
    épendance
    -0.38
     وتسجيلات
    -0.38
     <=",
    -0.36
    chables
    -0.36
    KeyListener
    -0.35
     constantemente
    -0.35
    POSITIVE LOGITS
     cuộc
    0.68
     simultaneous
    0.62
     partial
    0.62
    一场
    0.59
     unplanned
    0.58
     spontaneous
    0.58
    ครั้ง
    0.57
     successful
    0.57
    的一次
    0.56
     unsuccessful
    0.54
    Activations Density 1.035%

    No Known Activations